Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/captcha-sonic/agent-skills/captchasonic-solvenpx skills add Captcha-Sonic/Agent-skills --skill captchasonic-solvegit clone --depth 1 https://github.com/Captcha-Sonic/Agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/captcha-sonic/agent-skills/captchasonic-solve)<a href="https://agentmods.dev/skills/captcha-sonic/agent-skills/captchasonic-solve"><img src="https://agentmods.dev/badge/skills/captcha-sonic/agent-skills/captchasonic-solve.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00068 | $0.01293 |
| Opus 5 | $0.00034 | $0.00647 |
| Sonnet 5 | $0.00014 | $0.00259 |
| Haiku 4.5 | $0.00007 | $0.00129 |
Grade A, and why
captchasonic-solve scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Solve a CAPTCHA with CaptchaSonic
Use the CaptchaSonic MCP solve_captcha tool to solve any supported CAPTCHA type.
Prerequisites
The CaptchaSonic MCP server must be connected. If not set up yet, read references/mcp-setup.md or use the captchasonic-setup skill first.
Step 1: Identify the CAPTCHA Type
Determine the correct type parameter from the user's request:
| User Says | type Parameter |
Category |
|---|---|---|
| "PopularCaptcha grid" / "select all X" | PopularCaptchaImage |
Image (sync) |
| "reCAPTCHA v2 grid" | PopularCaptchaImage |
Image (sync) |
| "Geetest slide" | geetest_slide |
Image (sync) |
| "Geetest click" | geetest_click |
Image (sync) |
| "Geetest nine-grid" | geetest_nine |
Image (sync) |
| "OCR" / "text captcha" | ocr |
Image (sync) |
| "AWS WAF" | aws |
Image (sync) |
| "TikTok" | tiktok |
Image (sync) |
| "Binance slide" | binance |
Image (sync) |
| "Cloudflare Turnstile" | turnstile |
Token (async) |
| "reCAPTCHA v2 token" | recaptcha_v2 |
Token (async) |
| "reCAPTCHA v3 token" | recaptcha_v3 |
Token (async) |
Step 2: Gather Required Information
For image-based CAPTCHAs (sync):
type— the captcha type from the table abovequestion— the challenge text shown to the user (e.g., "Select all traffic lights")image_base64— base64-encoded PNG/JPEG image bytes- OR
image_url— public URL of the captcha image
- OR
For token-based CAPTCHAs (async):
type— the captcha type (e.g.,turnstile)question— can be empty or describe the taskwebsite_url— the page URL where the captcha appears
Step 3: Call the MCP Tool
Use the solve_captcha MCP tool with the gathered parameters.
Example for image captcha:
Tool: solve_captcha
Arguments:
type: "PopularCaptchaImage"
question: "Select all traffic lights"
image_base64: "<base64 encoded image>"
Example for token captcha:
Tool: solve_captcha
Arguments:
type: "turnstile"
question: "Cloudflare Turnstile"
website_url: "https://example.com"
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 132 lines · 68 tokens per session scan A f97328e2bd51
captchasonic-solve is a skill published in the GitHub repository Captcha-Sonic/Agent-skills (1 stars, last pushed 3mo ago), licensed MIT. It adds 68 tokens to every session and 1,293 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
fetch-crawl4ai
Deep URL fetch using crawl4ai (Playwright-powered) for JS-rendered pages, anti-bot sites, and dynamic content. Slower than fetch-jina but handles sites that block simple fetchers. Requires user-installed crawl4ai package.
auto-captcha-solver
Universal captcha auto-solver for Playwright browser automation. Detects hCaptcha and reCAPTCHA v2 on any page, solves via NopeCHA API, and injects tokens automatically. Drop-in CaptchaSolver class with autosolve(page) method.
playwright-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
chrome-devtools-cli
Use this skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.
a11y-debugging
Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.
chrome-devtools
Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to --slim mode (MCP configuration).